{"id":"https://openalex.org/W4285118488","doi":"https://doi.org/10.1109/tcsvt.2022.3177320","title":"Video Captioning Using Global-Local Representation","display_name":"Video Captioning Using Global-Local Representation","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4285118488","doi":"https://doi.org/10.1109/tcsvt.2022.3177320","pmid":"https://pubmed.ncbi.nlm.nih.gov/37215187"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3177320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3177320","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10198123/pdf/nihms-1840658.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051997091","display_name":"Liqi Yan","orcid":"https://orcid.org/0000-0002-7077-4947"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Liqi Yan","raw_affiliation_strings":["Westlake Institute for Advanced Study, Fudan University, Shanghai, China","Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA","School of Engineering, Westlake University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7077-4947","affiliations":[{"raw_affiliation_string":"Westlake Institute for Advanced Study, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I24943067"]},{"raw_affiliation_string":"Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016972157","display_name":"Siqi Ma","orcid":"https://orcid.org/0000-0003-3479-5713"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Ma","raw_affiliation_strings":["School of Engineering, Westlake University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, Menlo Park, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7570-5756","affiliations":[{"raw_affiliation_string":"Meta AI, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409186","display_name":"Yingjie Chen","orcid":"https://orcid.org/0000-0001-6705-3535"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingjie Chen","raw_affiliation_strings":["Department of Computer Graphics Technology, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6705-3535","affiliations":[{"raw_affiliation_string":"Department of Computer Graphics Technology, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107249133","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0002-9544-2500"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Department of Computer Graphics Technology, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Graphics Technology, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022041853","display_name":"Andreas Savakis","orcid":"https://orcid.org/0000-0002-9657-3027"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Savakis","raw_affiliation_strings":["Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9657-3027","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101979289","display_name":"Dongfang Liu","orcid":"https://orcid.org/0000-0001-6995-4775"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5051997091"],"corresponding_institution_ids":["https://openalex.org/I155173764","https://openalex.org/I24943067","https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":10.3532,"has_fulltext":true,"cited_by_count":107,"citation_normalized_percentile":{"value":0.98947944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":"10","first_page":"6642","last_page":"6656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9807297587394714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.840974748134613},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6120875477790833},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5764514207839966},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5638442635536194},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5373484492301941},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5359061360359192},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5268484354019165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5252639651298523},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5106745362281799},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4808928966522217},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45320916175842285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4490542709827423},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42890557646751404},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3140000104904175},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15030521154403687}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9807297587394714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840974748134613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6120875477790833},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5764514207839966},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5638442635536194},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5373484492301941},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5359061360359192},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5268484354019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252639651298523},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5106745362281799},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4808928966522217},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45320916175842285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4490542709827423},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42890557646751404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15030521154403687},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcsvt.2022.3177320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3177320","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmid:37215187","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37215187","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on circuits and systems for video technology : a publication of the Circuits and Systems Society","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10198123","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10198123","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10198123/pdf/nihms-1840658.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Circuits Syst Video Technol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10198123","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10198123","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10198123/pdf/nihms-1840658.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Circuits Syst Video Technol","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G2032842144","display_name":null,"funder_award_id":"1R25EY029127-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4285118488.pdf"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1677182931","https://openalex.org/W1956340063","https://openalex.org/W2016589492","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2119717200","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2148154194","https://openalex.org/W2425121537","https://openalex.org/W2507009361","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2549139847","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2607151106","https://openalex.org/W2625940279","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2782436336","https://openalex.org/W2799176631","https://openalex.org/W2806331055","https://openalex.org/W2807968599","https://openalex.org/W2887585070","https://openalex.org/W2905172366","https://openalex.org/W2938603906","https://openalex.org/W2940963663","https://openalex.org/W2948358897","https://openalex.org/W2962681491","https://openalex.org/W2962799512","https://openalex.org/W2962907269","https://openalex.org/W2962937869","https://openalex.org/W2962990649","https://openalex.org/W2962994439","https://openalex.org/W2963076818","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963524571","https://openalex.org/W2963620441","https://openalex.org/W2963645879","https://openalex.org/W2963699792","https://openalex.org/W2963971014","https://openalex.org/W2964345285","https://openalex.org/W2968101724","https://openalex.org/W2970060478","https://openalex.org/W2972281329","https://openalex.org/W2981411942","https://openalex.org/W2981750519","https://openalex.org/W2982515679","https://openalex.org/W2984862483","https://openalex.org/W2985144848","https://openalex.org/W2986953233","https://openalex.org/W2988753485","https://openalex.org/W2990307191","https://openalex.org/W2997199342","https://openalex.org/W3010071343","https://openalex.org/W3019301826","https://openalex.org/W3029267566","https://openalex.org/W3034221024","https://openalex.org/W3034593503","https://openalex.org/W3034815696","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3038528491","https://openalex.org/W3047922786","https://openalex.org/W3090602574","https://openalex.org/W3098682680","https://openalex.org/W3105136412","https://openalex.org/W3115684750","https://openalex.org/W3134875898","https://openalex.org/W3163971663","https://openalex.org/W3174490084","https://openalex.org/W3181286780","https://openalex.org/W3188394685","https://openalex.org/W3206120323","https://openalex.org/W4205510032","https://openalex.org/W4226174875","https://openalex.org/W6621543089","https://openalex.org/W6638667902","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6742667445","https://openalex.org/W6754478056","https://openalex.org/W6768853884","https://openalex.org/W6792405717","https://openalex.org/W6803023527"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Video":[0],"captioning":[1,43,135],"is":[2],"a":[3,46,51,55,71,90,111,150,155,176],"challenging":[4],"task":[5,44],"as":[6,175],"it":[7],"needs":[8],"to":[9,83,104,132],"accurately":[10],"transform":[11],"visual":[12],"understanding":[13,182],"into":[14],"natural":[15],"language":[16],"description.":[17],"To":[18],"date,":[19],"state-of-the-art":[20,147],"methods":[21,148],"inadequately":[22],"model":[23],"global-local":[24,56,92],"vision":[25,77],"representation":[26,57],"for":[27,34,109,179],"sentence":[28],"generation,":[29],"leaving":[30],"plenty":[31],"of":[32,114,163],"room":[33],"improvement.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,69,88,120,144,168],"approach":[40],"the":[41,65,122,139],"video":[42,81,97,115,181,185],"from":[45,79],"new":[47],"perspective":[48],"and":[49,102,141,166],"propose":[50,70],"GLR":[52,60,172],"framework,":[53],"namely":[54],"granularity.":[58],"Our":[59],"demonstrates":[61],"three":[62],"advantages":[63],"over":[64],"prior":[66],"efforts.":[67],"First,":[68],"simple":[72],"solution,":[73],"which":[74,94,126],"exploits":[75],"extensive":[76],"representations":[78,98],"different":[80,96],"ranges":[82],"improve":[84],"linguistic":[85],"expression.":[86],"Second,":[87],"devise":[89],"novel":[91],"encoder,":[93],"encodes":[95],"including":[99,149],"long-range,":[100],"short-range":[101],"local-keyframe,":[103],"produce":[105],"rich":[106],"semantic":[107],"vocabulary":[108],"obtaining":[110],"descriptive":[112],"granularity":[113],"contents":[116],"across":[117],"frames.":[118],"Finally,":[119],"introduce":[121],"progressive":[123],"training":[124,160],"strategy":[125],"can":[127],"effectively":[128],"organize":[129],"feature":[130],"learning":[131],"incur":[133],"optimal":[134],"behavior.":[136],"Evaluated":[137],"on":[138],"MSR-VTT":[140],"MSVD":[142],"dataset,":[143],"outperform":[145],"recent":[146],"well-tuned":[151],"SA-LSTM":[152],"baseline":[153,178],"by":[154],"significant":[156],"margin,":[157],"with":[158],"shorter":[159],"schedules.":[161],"Because":[162],"its":[164],"simplicity":[165],"efficacy,":[167],"hope":[169],"that":[170],"our":[171],"could":[173],"serve":[174],"strong":[177],"many":[180],"tasks":[183],"besides":[184],"captioning.":[186],"Code":[187],"will":[188],"be":[189],"available.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":61},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-07T08:38:57.713557","created_date":"2025-10-10T00:00:00"}
